AI Engineer | NYC

Starbridge•New York, NY

About The Position

We’re looking for an AI Engineer to help us build and scale the next generation of AI-powered systems at Starbridge. You’ll work on projects that sit at the core of our product—building, evaluating, and deploying LLM-driven features that make it easier for organizations to access, understand, and act on complex public data. You’ll collaborate closely with our engineering and product teams to design new AI capabilities, such as deep document analysis and interactive chat experiences. This role combines hands-on software engineering, applied machine learning, and product experimentation, with the goal of delivering reliable, high-performing AI systems to production. You’ll have the opportunity to work with models from OpenAI, Anthropic, and Gemini , contribute to our AI infrastructure, and play a key role in shaping how we leverage generative AI across our platform.

Requirements

Bachelor’s degree in Computer Science, Engineering, Mathematics, related field, or equivalent experience
High level of coding proficiency using Python
5+ years of professional experience in software engineering, AI/ML development including:
Proficiency with production software (Python) and systems design
Machine learning algorithms and model development techniques
ML lifecycle tools like MLflow, dvc, weights & biases
Cloud deployment of ML systems
Professional experience with LLMs and large-scale models
Very strong software engineering skills with a track record of building scalable, distributed product machine learning systems
Strong analytical and problem-solving skills
Ability to communicate complex ideas and concepts effectively
Ability to work independently and collaboratively

Nice To Haves

Experience building scalable applications with LLMs, using frameworks such as LangChain, LlamaIndex, Hugging Face, etc
Depth of knowledge with RAG implementation and improvements

Responsibilities

Collaborate closely with our team as we productize new AI-powered capabilities: such as AI proposal writing & search experiences.
Evaluate the performance of AI models (we will work with models from OpenAI, Anthropic, Gemini) & systems through rigorous testing and experimentation.
Stay up-to-date with the latest advancements in AI and machine learning research, and proactively suggest improvements to enhance our generative AI capabilities.
Implement strong testing and CI/CD practices that help us move with confidence in our AI system development